EDVD-LLaMA: Explainable Deepfake Video Detection via Multimodal Large Language Model Reasoning
cs.CV, cs.AI
Submitted: 2025-10-18
Updated: 2026-11-16
Code: https://github.com/davisking/dlib
Project page: https://11ouo1.github.io/edvd-llama
Terminology
Sources
- ExDDV: A New Dataset for Explainable Deepfake Detection in Video
- AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models
- Qwen2.5-VL Technical Report
- FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping
- Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
- VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs